home / skills / sickn33 / antigravity-awesome-skills / backtesting-frameworks

backtesting-frameworks skill

needs review

This skill helps you build robust backtesting frameworks by modeling look-ahead biases, walk-forward testing, and cost-aware simulations.

This is most likely a fork of the backtesting-frameworks skill from xfstudio

npx playbooks add skill sickn33/antigravity-awesome-skills --skill backtesting-frameworks

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

1.4 KB

---
name: backtesting-frameworks
description: Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.
---

# Backtesting Frameworks

Build robust, production-grade backtesting systems that avoid common pitfalls and produce reliable strategy performance estimates.

## Use this skill when

- Developing trading strategy backtests
- Building backtesting infrastructure
- Validating strategy performance and robustness
- Avoiding common backtesting biases
- Implementing walk-forward analysis

## Do not use this skill when

- You need live trading execution or investment advice
- Historical data quality is unknown or incomplete
- The task is only a quick performance summary

## Instructions

- Define hypothesis, universe, timeframe, and evaluation criteria.
- Build point-in-time data pipelines and realistic cost models.
- Implement event-driven simulation and execution logic.
- Use train/validation/test splits and walk-forward testing.
- If detailed examples are required, open `resources/implementation-playbook.md`.

## Safety

- Do not present backtests as guarantees of future performance.
- Avoid providing financial or investment advice.

## Resources

- `resources/implementation-playbook.md` for detailed patterns and examples.

Overview

This skill teaches how to build robust backtesting systems for trading strategies that reduce look-ahead bias, survivorship bias, and unrealistic transaction assumptions. It focuses on producing reliable performance estimates through point-in-time data, realistic cost models, and proper train/validation/test splits. Use it to validate strategies, implement walk-forward testing, and create production-grade backtesting infrastructure.

How this skill works

I guide the construction of event-driven simulators that consume point-in-time market data and realistic fill/fee/slippage models. The approach enforces strict data versioning, universe survivorship handling, and time-aware feature construction so signals never access future information. Walk-forward testing and rolling train/validation/test splits are used to assess robustness across market regimes.

When to use it

Developing or validating algorithmic trading strategies before live deployment
Building backtesting infrastructure for research or production use
Detecting and eliminating look-ahead and survivorship biases in results
Comparing strategy variants with consistent cost and execution models
Implementing walk-forward analysis and out-of-sample testing

Best practices

Define hypothesis, universe, timeframe, and explicit evaluation metrics before coding
Use point-in-time snapshots for prices, fundamentals, and any derived features
Model transaction costs, slippage, and realistic fills rather than assuming mid-price fills
Split data into train/validation/test with no temporal leakage and apply walk-forward validation
Log and version input data, parameter sets, and random seeds for reproducibility

Example use cases

Backtesting a factor-based equity strategy while excluding delisted stocks to avoid survivorship bias
Building an event-driven simulator for intraday execution with queue impact and slippage models
Validating a momentum strategy with rolling walk-forward optimization and out-of-sample performance tracking
Comparing portfolio construction methods under identical transaction cost and turnover constraints
Stress-testing strategies across different market regimes and volatility states

FAQ

Does this skill provide live trading execution?

No. The skill focuses on backtesting and validation; it does not implement live order routing or broker integrations.

How do I avoid look-ahead bias?

Construct features and signals using only data available at each decision timestamp and use point-in-time snapshots for any historical datasets.